Guest Editors
Prof. Gianni D'Angelo
Email: giadangelo@unisa.it
Affiliation: Department of Computer Science, University of Salerno, Fisciano, Italy
Homepage:
Research Interests: intrusion detection systems (IDS) design and evaluation, application of artificial intelligence and machine learning to threat detection, deep learning for anomaly and network traffic analysis, cyber threat intelligence for emerging threats; security analytics, feature extraction, and automated detection techniques, scalable and distributed IDS for cloud and enterprise environments
Prof. Arcangelo Castiglione
Email: arcastiglione@unisa.it
Affiliation: Department of Computer Science, University of Salerno, Fisciano, Italy
Homepage:
Research Interests: applied cryptography & lightweight security, blockchain & decentralized systems, IoT, smart systems & cloud security
Summary
All major cybersecurity reports consistently highlight a dramatic increase in cyber incidents over recent years. Not only is the frequency of attacks rising, but their scale, sophistication, and impact are intensifying as well. This escalation results in substantial economic losses. For instance, the four largest European economies—Italy, France, Germany, and Spain—collectively suffered losses exceeding €300 billion due to cyber attacks between 2020 and 2025.
Such a scenario underscores the urgent need for resilient and adaptive defensive strategies capable of addressing both current and emerging cyber threats. Traditional security mechanisms alone are no longer sufficient to cope with highly dynamic, stealthy, and intelligent attack techniques.
In this evolving threat landscape, Intrusion Detection Systems (IDS) remain fundamental components of cybersecurity infrastructures. An intrusion refers to any attempt to compromise the confidentiality, integrity, or availability of digital resources, or to bypass the security mechanisms of computer systems and networks. IDS are designed to monitor system and network activities, analyze events in real time, and identify suspicious or malicious behavior. Upon detecting anomalies or potential threats, they generate alerts to enable timely response and mitigation.
However, contemporary adversaries employ increasingly sophisticated tactics, including zero-day exploits, advanced persistent threats, AI-driven attacks, and distributed campaigns that continuously mutate their behavior. To effectively counter these challenges, IDS must evolve beyond static rule-based approaches and become resilient, adaptive, scalable, and robust systems capable of learning from new attack patterns and operating effectively in complex, distributed, and resource-constrained environments.
The RAIDS Special Issue aims to advance research on next-generation Intrusion Detection Systems designed to address emerging cyber threats through resilience and adaptability. Particular attention will be devoted to intelligent and data-driven approaches, including artificial intelligence, machine learning, deep learning, distributed detection paradigms, and collaborative defense mechanisms. Emphasis will also be placed on efficiency, scalability, and sustainability, ensuring that advanced detection capabilities can be deployed in real-world environments without excessive computational or environmental costs.
Topics of interest include, but are not limited to:
· Machine Learning and Artificial Intelligence for Resilient Intrusion Detection
· Datasets and Benchmarking Frameworks for Evaluating Adaptive IDS
· Distributed, Collaborative, and Federated Intrusion Detection Systems
· Privacy, Legal, Ethical, and Social Implications of Intelligent IDS
· Deep Learning Architectures for Adaptive Threat Detection
· Scalable and Energy-Efficient Intrusion Detection Solutions
· Novel Intrusion Detection Techniques and Algorithms for Emerging Threats
· Metrics for Evaluating Resilience, Adaptability, and Social Impact
Keywords
intrusion detection systems (IDS), resilient cybersecurity, adaptive security systems, emerging cyber threats, artificial intelligence, machine learning, deep learning, anomaly detection, distributed intrusion detection, sustainable cyber defense
Login
Register
Submit a Paper
Propose a Special lssue